CN110703760B - Newly-added suspicious object detection method for security inspection robot - Google Patents
Newly-added suspicious object detection method for security inspection robot Download PDFInfo
- Publication number
- CN110703760B CN110703760B CN201911041115.4A CN201911041115A CN110703760B CN 110703760 B CN110703760 B CN 110703760B CN 201911041115 A CN201911041115 A CN 201911041115A CN 110703760 B CN110703760 B CN 110703760B
- Authority
- CN
- China
- Prior art keywords
- robot
- patrol
- image
- algorithm
- points
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0231—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
- G05D1/0238—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using obstacle or wall sensors
- G05D1/024—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using obstacle or wall sensors in combination with a laser
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
- G05D1/0221—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory involving a learning process
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0231—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
- G05D1/0246—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using a video camera in combination with image processing means
- G05D1/0253—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using a video camera in combination with image processing means extracting relative motion information from a plurality of images taken successively, e.g. visual odometry, optical flow
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0255—Control of position or course in two dimensions specially adapted to land vehicles using acoustic signals, e.g. ultra-sonic singals
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0257—Control of position or course in two dimensions specially adapted to land vehicles using a radar
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0276—Control of position or course in two dimensions specially adapted to land vehicles using signals provided by a source external to the vehicle
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0276—Control of position or course in two dimensions specially adapted to land vehicles using signals provided by a source external to the vehicle
- G05D1/028—Control of position or course in two dimensions specially adapted to land vehicles using signals provided by a source external to the vehicle using a RF signal
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Abstract
The invention provides a newly added suspicious object detection method for a security inspection robot, which comprises the following steps: manually controlling the security inspection robot to walk once along the inspection route, acquiring peripheral distance information by a laser radar sensor in the process, and constructing an environment map by using an SLAM algorithm; step (2): setting a plurality of fixed patrol points in a patrol line, and automatically taking a multi-angle picture at each patrol point by a cradle head camera as a reference picture; the existing method for removing hidden troubles of newly added suspicious objects by means of regular patrol or installation monitoring of security personnel can consume larger manpower and material resources. In contrast, the invention adopts the robot and the image processing technology to automatically detect newly added suspicious objects in the fixed area, thereby not only having high automation degree; the data record is electronic, so that the site situation and information can be completely presented; and greatly reduces the labor cost.
Description
Technical Field
The invention relates to the technical field of security robots, in particular to a newly added suspicious object detection method for a security inspection robot.
Background
In relatively open areas such as factory buildings, community fire-fighting channels, underground garages and the like, with fewer personnel, some redundant suspicious objects often exist. Some objects may be randomly placed and discarded, but may prevent safe production or block a fire escape passage; some may be toxic and harmful dangerous objects deliberately placed by lawbreakers, which may have immeasurable security consequences for society. At present, each factory and each district mainly eliminates hidden dangers by arranging security personnel to patrol or install and monitor regularly, but the security personnel has limited manpower and higher manpower cost, and the monitoring often has dead angles, unclear pictures and other problems.
With the development of electronic industry technology and artificial intelligence technology, robots are playing an increasingly important role in actual production and life. The robot has the advantages of high automation degree, accurate data acquisition, high working efficiency and the like, and can replace manpower in certain labor-intensive fields, so that the manpower cost is greatly reduced.
Disclosure of Invention
In view of the above, the invention provides a new suspicious object detection method for a security inspection robot. The robot can automatically send information and screenshot to security personnel when the newly-added object appears, and the security personnel can judge whether the object is suspicious and process the object, so that the security efficiency is improved and the hidden danger rate is reduced. In order to achieve the above purpose, the present invention provides the following technical solutions:
the security inspection robot for detecting newly added suspicious objects comprises a basic structure of the robot, a navigation obstacle avoidance system, a visual analysis system and a communication system. The navigation obstacle avoidance system mainly takes charge of tasks such as path planning, obstacle avoidance, return to a fixed patrol point and the like by sensors such as a laser radar, an ultrasonic module, a three-axis gyroscope and the like; the visual analysis system consists of a tripod head camera, a DSP (Digital Signal Processor, a digital signal processor) and the like and is mainly responsible for tasks such as image acquisition, image algorithm analysis and the like; the communication system is responsible for bidirectional data transmission between the robot and the background and is used for sending and transmitting man-machine interaction information.
The newly added suspicious object detection method for the security inspection robot approximately comprises the following steps:
step (1): manually controlling the security inspection robot to walk once along the inspection route, acquiring peripheral distance information by a laser radar sensor in the process, and constructing an environment map by using a SLAM (Simultaneous Localization and Mapping) algorithm;
step (2): setting a plurality of fixed patrol points in a patrol line, and automatically taking a multi-angle picture at each patrol point by a cradle head camera as a reference picture;
step (3): the security inspection robot automatically inspects according to a preset path and a constructed environment map, and when the ultrasonic module detects that an obstacle exists in front, the robot automatically avoids the obstacle according to an obstacle avoidance algorithm;
step (4): when the security inspection robot arrives at a preset patrol point, the cradle head camera shoots surrounding images again, and compares the surrounding images with the original reference picture by adopting an image registration and difference algorithm, so as to intelligently analyze whether new objects appear in surrounding scenes;
step (5): when the security inspection robot judges that new objects appear around, the corresponding information and screenshot are transmitted to a background security personnel through a communication system, and the security personnel judges whether the objects are suspicious and process the objects.
Compared with the prior art, the invention has the beneficial effects that:
the existing method for removing hidden troubles of newly added suspicious objects by means of regular patrol or installation monitoring of security personnel can consume larger manpower and material resources. In contrast, the invention adopts the robot and the image processing technology to automatically detect newly added suspicious objects in the fixed area, thereby not only having high automation degree; the data record is electronic, so that the site situation and information can be completely presented; and greatly reduces the labor cost.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is an overall flowchart of a method for detecting newly added suspicious objects for a security inspection robot according to an embodiment of the present invention;
fig. 2 is a detailed flowchart of an image detection section provided in an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are only some, but not all embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to fall within the scope of the invention.
The embodiment of the invention provides a flow chart of a newly added suspicious object detection method for a security inspection robot. As shown in fig. 1, it mainly comprises the following steps:
step (1): the manual control security inspection robot walks once along the inspection route, and in the process, the laser radar sensor obtains peripheral distance information, and the observed value z of the external environment generally comprises the distance r and the angle theta between the environmental road sign and the laser radar, and can be expressed as:
the observation model of the lidar is related to the measured distance and angle and also the current coordinates of the robot, and can be generally expressed as:
z k ＝h(x k )
wherein x is k Coordinate of robot at time k, z k The coordinates of the environmental observation at the time k are further obtained:
wherein, (x) i ,y i ) Is the coordinates of the i-th environmental feature observed. On-line derivativeAnd obtaining an observation model h, namely an environment map to be constructed.
Step (2): several fixed patrol points are artificially set in the patrol line, and a multi-angle picture is automatically shot by a tripod head camera at each patrol point to serve as a reference picture.
(2.1), setting m fixed patrol points in the patrol line, such as heavy point areas of a passageway entrance, a corner and the like.
(2.2), selecting n angles at each fixed point, and shooting a high-definition image at each angle, wherein the resolution of the image is larger than 1280 multiplied by 720.
(2.3) finally obtaining m multiplied by n images, and recording the position coordinates (x, y) and azimuth angle (alpha), lens pitch angle (gamma) and stretching multiple(s) of the robot while shooting each image.
Step (3): the security inspection robot automatically inspects according to a preset path and a constructed environment map, and when the ultrasonic module detects that an obstacle exists in front, the robot automatically avoids the obstacle according to an obstacle avoidance algorithm.
(3.1) when the robot is at a certain point, the laser radar acquires the current environment observation value z k According to the environmental map model h obtained in the step (1), the current coordinate position x can be obtained k ：
x k ＝h -1 (z k )
(3.2) knowing the position x of the robot at the next moment according to the preset path k+1 The orientation and distance the robot should adjust can then be found:
Δx＝x k+1 -x k 。
step (4): when the robot arrives at a preset patrol point, the cradle head camera shoots the surrounding image again, and compares the surrounding image with the original reference picture by adopting an image registration and difference algorithm, and intelligently analyzes whether a new object appears in the surrounding scene, wherein the specific steps are shown in fig. 2.
(4.1) when the robot reaches a certain preset patrol point (x, y), searching corresponding azimuth angle (alpha), lens pitch angle (gamma) and stretching multiple(s) according to the record, and achieving the same state.
(4.2) taking a picture of the current time in the same state, since the states of the two times are not exactly the same, the registration process is required for the image. Firstly, acquiring key points and corresponding feature descriptions of two images by adopting a SURF algorithm; then adopting knn algorithm to calculate the distance of descriptors between each pair of key points, returning the minimum distance in k best matches of each key point, and adopting Ranac algorithm to eliminate mismatching points so as to reduce matching errors; and finally, calculating a homography transformation matrix between the two graphs for the reserved matching points by adopting a Homographies algorithm.
And (4.3) after registration is completed, obtaining the places with different images, namely suspected newly added objects, by using an image difference algorithm. Subtracting the front image and the rear image to obtain the absolute value of the pixel value difference at the corresponding position of the image, and judging whether the absolute value is larger than a certain threshold value or not:
wherein D (x, y) is the obtained differential image, and I (t) and I (t-1) are respectively the front and rear images after registration.
(4.4) carrying out connected domain statistics in the 8 fields on the differential image so as to obtain pixel point information adhered together, and filtering pixels which do not meet the condition, wherein the filtering condition is as follows:
(1) the number of the adhered pixels is less than 0.01 of the number of the pixels of the whole image, and the adhered pixels can be regarded as noise or caused by slight shaking of leaves and the like;
(2) differential stuck pixels still occur at the object edge contours due to errors in the registration algorithm, but such stuck pixels are typically relatively slender in shape, thus filtering out stuck pixel areas with aspect ratios greater than 5.
And (4.5) finally obtaining a reserved adhered pixel point area, and returning the adhered pixel point area to the original picture frame.
Step (5): when the security inspection robot judges that new objects appear around, the corresponding information and screenshot are transmitted to a background security personnel through a communication system, and the security personnel judges whether the objects are suspicious and process the objects.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
While specific examples have been described herein for the purpose of illustrating the principles and embodiments of the present invention, the above examples are provided solely to assist in understanding the manner in which the present invention may be practiced and the core ideas thereof, and it should be noted that there are objectively no particular arrangements, as the text is limited, and that several modifications, adaptations, or variations may be made by one of ordinary skill in the art without departing from the principles of the present invention, and that the foregoing general inventive concept may be combined in any suitable manner; such modifications, variations and combinations, or the direct application of the inventive concepts and aspects to other applications without modification, are contemplated as falling within the scope of the present invention.
Claims (2)
1. The newly-added suspicious object detection method for the security inspection robot is characterized by comprising the following steps of:
step (1): manually controlling the security inspection robot to walk once along the inspection route, acquiring peripheral distance information by a laser radar sensor in the process, and constructing an environment map by using an SLAM algorithm;
step (2): setting a plurality of fixed patrol points in a patrol line, and automatically taking a multi-angle picture at each patrol point by a cradle head camera as a reference picture;
step (3): the security inspection robot automatically inspects according to a preset path and a constructed environment map, and when the ultrasonic module detects that an obstacle exists in front, the robot automatically avoids the obstacle according to an obstacle avoidance algorithm;
step (4): when the security inspection robot arrives at a preset patrol point, the cradle head camera shoots surrounding images again, and compares the surrounding images with the original reference picture by adopting an image registration and difference algorithm, so as to intelligently analyze whether new objects appear in surrounding scenes;
step (5): when the security inspection robot judges that new objects appear around, the corresponding information and screenshot are transmitted to a background security personnel through a communication system, and the security personnel judges whether the objects are suspicious and process the objects;
the specific method of the step (2) is as follows:
(2.1) setting m fixed patrol points in the patrol line, wherein the fixed patrol points are key areas at the entrance and the exit of the channel and the corners;
(2.2) selecting n angles at each fixed point, and shooting a high-definition image at each angle, wherein the resolution of the image is larger than 1280 multiplied by 720;
(2.3) finally obtaining m multiplied by n images, and recording the position coordinates (x, y) and azimuth angle alpha of the robot, the pitch angle gamma of the lens and the stretching multiple s when shooting each image;
the specific method of the step (4) is as follows:
(4.1) when the robot reaches a certain preset patrol point (x, y), searching the corresponding azimuth angle alpha, the lens pitch angle gamma and the stretching multiple s according to the record, and achieving the same state;
(4.2) taking a picture of the current moment in the same state, wherein the states of the front and back two times cannot be completely the same, so that the registration processing is required to be carried out on the images;
firstly, acquiring key points and corresponding feature descriptions of two images by adopting a SURF algorithm; then adopting knn algorithm to calculate the distance of descriptors between each pair of key points, returning the minimum distance in k best matches of each key point, and adopting Ranac algorithm to eliminate mismatching points so as to reduce matching errors; finally, homographies algorithm is adopted to calculate homography transformation matrix between two graphs for the reserved matching points;
(4.3) after registration is completed, obtaining different places of the two images, namely suspected newly added objects, by using an image difference algorithm; subtracting the front image and the rear image to obtain the absolute value of the pixel value difference at the corresponding position of the image, and judging whether the absolute value is larger than a certain threshold value or not:
d (x, y) is a calculated differential image, and I (t) and I (t-1) are respectively a front picture and a rear picture which are registered;
(4.4) carrying out connected domain statistics in the 8 fields on the differential image so as to obtain pixel point information adhered together, and filtering pixels which do not meet the condition, wherein the filtering condition is as follows:
(1) the number of the adhered pixels is less than 0.01 of the number of the pixels of the whole image, and the adhered pixels are considered to be noise points or caused by slight swaying of leaves;
(2) because of the error of the registration algorithm, differential stuck pixel points still can be generated at the edge contour of the object, but the shape of the stuck pixel points is generally slender, so that the stuck pixel point area with the length-width ratio larger than 5 is filtered out;
and (4.5) finally obtaining a reserved adhered pixel point area, and returning the adhered pixel point area to the original picture frame.
2. The method for detecting newly added suspicious objects for the security inspection robot according to claim 1, wherein the specific method of the step (3) is as follows:
(3.1) when the robot is at a certain point, the laser radar acquires the current environment observation value z k According to the environmental map model h obtained in the step (1), the current coordinate position x can be obtained k ：
x k ＝h -1 (z k )
(3.2) knowing the position x of the robot at the next moment according to the preset path k+1 The orientation and distance the robot should adjust can then be found:
Δx＝x k+1 -x k 。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911041115.4A CN110703760B (en) | 2019-10-30 | 2019-10-30 | Newly-added suspicious object detection method for security inspection robot |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911041115.4A CN110703760B (en) | 2019-10-30 | 2019-10-30 | Newly-added suspicious object detection method for security inspection robot |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110703760A CN110703760A (en) | 2020-01-17 |
| CN110703760B true CN110703760B (en) | 2023-06-02 |
Family
ID=69202719
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911041115.4A Active CN110703760B (en) | 2019-10-30 | 2019-10-30 | Newly-added suspicious object detection method for security inspection robot |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110703760B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112908039B (en) * | 2021-01-27 | 2022-02-25 | 深圳协鑫智慧能源有限公司 | Airspace control method based on intelligent street lamp and intelligent street lamp |
| CN113673614B (en) * | 2021-08-25 | 2023-12-12 | 北京航空航天大学 | Metro tunnel foreign matter intrusion detection device and method based on machine vision |
| CN114248271B (en) * | 2021-12-31 | 2024-04-09 | 上海科建工程管理股份有限公司 | Inspection robot system and operation method thereof |
| CN115273459A (en) * | 2022-06-25 | 2022-11-01 | 河南机电职业学院 | Unmanned safety cruiser |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2001117633A (en) * | 1999-10-20 | 2001-04-27 | Babcock Hitachi Kk | Plant-monitoring method |
| CN102930277A (en) * | 2012-09-19 | 2013-02-13 | 上海珍岛信息技术有限公司 | Character picture verification code identifying method based on identification feedback |
| CN104581054A (en) * | 2014-12-22 | 2015-04-29 | 深圳供电局有限公司 | Electric transmission line inspecting method and system based on videos |
| CN104851094A (en) * | 2015-05-14 | 2015-08-19 | 西安电子科技大学 | Improved method of RGB-D-based SLAM algorithm |
| CN206363159U (en) * | 2016-11-25 | 2017-07-28 | 东莞市万科建筑技术研究有限公司 | A kind of community security patrol robot system |
| CN106991695A (en) * | 2017-03-27 | 2017-07-28 | 苏州希格玛科技有限公司 | A kind of method for registering images and device |
| CN108107904A (en) * | 2017-12-18 | 2018-06-01 | 柳州铁道职业技术学院 | A kind of patrolling railway and contact net for power supplying foreign matter based on multi-rotor unmanned aerial vehicle remove system and its method for patrolling railway |
| CN109359649A (en) * | 2017-12-28 | 2019-02-19 | 广州Tcl智能家居科技有限公司 | A kind of recognition methods of access object, storage medium and the article-storage device of article-storage device |
| CN109599945A (en) * | 2018-11-30 | 2019-04-09 | 武汉大学 | A kind of autonomous crusing robot cruising inspection system of wisdom power plant and method |
| CN110163036A (en) * | 2018-03-06 | 2019-08-23 | 腾讯科技（深圳）有限公司 | A kind of image-recognizing method and device |
-
2019
- 2019-10-30 CN CN201911041115.4A patent/CN110703760B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2001117633A (en) * | 1999-10-20 | 2001-04-27 | Babcock Hitachi Kk | Plant-monitoring method |
| CN102930277A (en) * | 2012-09-19 | 2013-02-13 | 上海珍岛信息技术有限公司 | Character picture verification code identifying method based on identification feedback |
| CN104581054A (en) * | 2014-12-22 | 2015-04-29 | 深圳供电局有限公司 | Electric transmission line inspecting method and system based on videos |
| CN104851094A (en) * | 2015-05-14 | 2015-08-19 | 西安电子科技大学 | Improved method of RGB-D-based SLAM algorithm |
| CN206363159U (en) * | 2016-11-25 | 2017-07-28 | 东莞市万科建筑技术研究有限公司 | A kind of community security patrol robot system |
| CN106991695A (en) * | 2017-03-27 | 2017-07-28 | 苏州希格玛科技有限公司 | A kind of method for registering images and device |
| CN108107904A (en) * | 2017-12-18 | 2018-06-01 | 柳州铁道职业技术学院 | A kind of patrolling railway and contact net for power supplying foreign matter based on multi-rotor unmanned aerial vehicle remove system and its method for patrolling railway |
| CN109359649A (en) * | 2017-12-28 | 2019-02-19 | 广州Tcl智能家居科技有限公司 | A kind of recognition methods of access object, storage medium and the article-storage device of article-storage device |
| CN110163036A (en) * | 2018-03-06 | 2019-08-23 | 腾讯科技（深圳）有限公司 | A kind of image-recognizing method and device |
| CN109599945A (en) * | 2018-11-30 | 2019-04-09 | 武汉大学 | A kind of autonomous crusing robot cruising inspection system of wisdom power plant and method |
Non-Patent Citations (3)
| Title |
|---|
| 智能巡检机器人视频监测皮带异物自动识别报警技术研究;高小强;《电子技术与软件工程》;20160615(第11期);158-160 * |
| 智能机器人在变电站巡检系统中的应用;蒋体浩 等;《电子世界》;20160930(第18期);88-89 * |
| 罗庆生 等.图像差分检测技术的研究与探索.《智能作战机器人》.2013, * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110703760A (en) | 2020-01-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110703760B (en) | Newly-added suspicious object detection method for security inspection robot | |
| CN108564065B (en) | Cable tunnel open fire identification method based on SSD | |
| CN110142785A (en) | A kind of crusing robot visual servo method based on target detection | |
| CN109872483B (en) | Intrusion alert photoelectric monitoring system and method | |
| JP4169282B2 (en) | Photogrammetry system and photogrammetry method | |
| CN112489371B (en) | Swimming pool drowning prevention early warning system based on computer vision | |
| CN111368615B (en) | Illegal building early warning method and device and electronic equipment | |
| CN112793564A (en) | Autonomous parking auxiliary system based on panoramic aerial view and deep learning | |
| CN111985365A (en) | Straw burning monitoring method and system based on target detection technology | |
| CN109828267A (en) | The Intelligent Mobile Robot detection of obstacles and distance measuring method of Case-based Reasoning segmentation and depth camera | |
| CN110012268A (en) | Pipe network AI intelligent control method, system, readable storage medium storing program for executing and equipment | |
| CN107729850A (en) | Broadcast system is supervised in Internet of Things outdoor advertising | |
| CN113435278A (en) | Crane safety detection method and system based on YOLO | |
| CN110209196A (en) | A kind of unmanned plane garden night watching method and system | |
| CN111967396A (en) | Processing method, device and equipment for obstacle detection and storage medium | |
| CN115880231A (en) | Power transmission line hidden danger detection method and system based on deep learning | |
| CN102291568A (en) | Accelerated processing method of large-view-field intelligent video monitoring system | |
| CN116453278A (en) | Intrusion monitoring method combining deep learning intelligent detection and optical fiber vibration sensing | |
| CN114677640A (en) | Intelligent construction site safety monitoring system and method based on machine vision | |
| US20210357654A1 (en) | Systems and methods of identifying persons-of-interest | |
| CN113763484A (en) | Ship target positioning and speed estimation method based on video image analysis technology | |
| WO2020211593A1 (en) | Digital reconstruction method, apparatus, and system for traffic road | |
| CN108334070B (en) | Robot running control method, device and system based on panoramic camera | |
| CN115035470A (en) | Low, small and slow target identification and positioning method and system based on mixed vision | |
| CN115134578A (en) | Super-fusion management platform with AR technology |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: A New Suspicious Object Detection Method for Security Patrol Robots Effective date of registration: 20231007 Granted publication date: 20230602 Pledgee: Guotou Taikang Trust Co.,Ltd. Pledgor: HANGZHOU XUJIAN SCIENCE AND TECHNOLOGY Co.,Ltd. Registration number: Y2023980059619 |
|
| PE01 | Entry into force of the registration of the contract for pledge of patent right |